Legal Case Retrieval Large Language Model Evaluation Datasets

We collected and organized a 11.3MB legal model evaluation dataset for case retrieval, which is stored in JSON format (*. json). The dataset consists of two files: Case_Setroval_Satasets.json and Case_Setroval_Satasets_llm.json. Among them, the Case_Setroval_Satasets.json file contains preprocessed datasets for various tasks, specifically designed for evaluating and testing large language models, with a data volume of 3.73MB. On the other hand, the Case_Setroval_Satasets_llm.json file adds a comprehensive dataset of large language model prediction results based on the former, with a data size of 7.66MB.